© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 54751
    Prev
    Next
    INDEX
    Explanations

    symbols used in a variety of contexts, likely including formatting or coding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erson
    -0.09
    ract
    -0.08
    ese
    -0.08
    uyá»ĩt
    -0.08
    енд
    -0.07
    rog
    -0.07
    utom
    -0.07
    skyt
    -0.07
    porte
    -0.07
    etsk
    -0.07
    POSITIVE LOGITS
     else
    0.08
    ï¸ı
    0.07
    ius
    0.07
    زÙĬز
    0.07
    de
    0.07
    phans
    0.06
    vette
    0.06
    .scalablytyped
    0.06
    ::|
    0.06
    u
    0.06
    Activations Density 0.153%

    No Known Activations